arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.04078math.OC
收藏

黎曼梯度法与动量

Riemannian Gradient Method with Momentum

Sapienza University of Rome(罗马第一大学)

Filippo Leggio, Diego Scuppa

AI总结:

本文提出了一种结合动量的黎曼梯度法,用于在黎曼流形上高效求解优化问题,通过理论分析和实验验证展示了其在复杂问题中的优越性能。

摘要:

本文考虑在黎曼流形上最小化光滑函数的问题,并提出一种黎曼梯度法与动量相结合的方法。所提出算法是对最近引入的无约束优化方法的一种重要且非平凡的扩展。我们证明,该算法通过一种保护规则,能够在最坏情况下以O(ε^{-2})的复杂度界产生一个ε-驻点。在基准问题上进行了大量的计算实验,将所提方法与Manopt包中现有的最先进求解器进行比较。结果表明,所提方法在竞争中表现优异,有时甚至更优。总体而言,数值证据证实了所提方法的有效性和鲁棒性,该方法为最近引入的基于动量的方法在黎曼优化中的扩展提供了有意义的扩展。

英文摘要:

In this paper, we consider the problem of minimizing a smooth function on a Riemannian manifold and present a Riemannian gradient method with momentum. The proposed algorithm represents a substantial and nontrivial extension of a recently introduced method for unconstrained optimization. We prove that the algorithm, supported by a safeguarding rule, produces an $ε$-stationary point with a worst-case complexity bound of $\mathcal{O}(ε^{-2})$. Extensive computational experiments on benchmark problems are carried out, comparing the proposed method with state-of-the-art solvers available in the Manopt package. The results demonstrate competitive and often superior performance. Overall, the numerical evidence confirms the effectiveness and robustness of the proposed approach, which provides a meaningful extension of the recently introduced momentum-based method to Riemannian optimization.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑